“Anthropogenic climate change has caused more frequent and widespread large fires in the western United States (US). Interpretable and accurate methods that can predict large fires in advance and at a high spatial resolution are essential for more targeted fire risk mitigation strategies, but the trade-off between accuracy and interpretability persists in current fire models. For example, machine learning (ML) fire models can be more accurate than process models but operate as “black-boxes” with a poor understanding of fire physics. Process fire models are more physically interpretable but remain less accurate than ML models. This research offers a novel perspective on the tradeoff and quantification of model physical interpretability and accuracy for wildfire predictions in the western US. More importantly, this study proposes a more interpretable and accurate ML fire model that explicitly incorporates fire knowledge while leveraging data-informed modeling advantages. The model predicted fire risk showed high consistency with actually occurred fire events, and revealed strong and multivariate climate controls on large fires and megafires in the western US. Our proposed fire model enables better predictions and understanding of large fires and megafires in the western US.” – From the plain language text of the paper.
Check out the details:
Li, F.; Zhu Q.; Yuan, K.; Ji, F.; Paul, A.; Lee, P.; Radeloff, V. C.; Chen, M. Projecting large fires in the western US with an interpretable and accurate hybrid machine learning method. Earths Future 2024. 12, e2024EF004588. https://doi.org/10.1029/2024EF004588